Arbitrary-view human action recognition via novel-view action generation

作者：

Highlights：

• We propose a two-branch novel-view action generation approach for arbitrary-view action recognition.

• The two-branch generation model generates novel-view action samples, which enlarges the view range of action samples for classifier training.

• A view-domain generalization module is designed to weaken the difference of action representation in various views for the arbitrary-view action recognition.

• Extensive experiments and ablation studies are performed on three large-scale benchmarks, UESTC, NTU-60 and NTU-120 datasets.

摘要

•We propose a two-branch novel-view action generation approach for arbitrary-view action recognition.•The two-branch generation model generates novel-view action samples, which enlarges the view range of action samples for classifier training.•A view-domain generalization module is designed to weaken the difference of action representation in various views for the arbitrary-view action recognition.•Extensive experiments and ablation studies are performed on three large-scale benchmarks, UESTC, NTU-60 and NTU-120 datasets.

论文关键词：Arbitrary-view action recognition,Novel-view action generation,View domain generalization

论文评审过程：Received 2 June 2020, Revised 25 January 2021, Accepted 11 May 2021, Available online 20 May 2021, Version of Record 28 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108043